Stock Trading Decision Method Based on Stop Loss Double Threshold

Abstract

Artificial intelligence technology is widely used in stock market stock forecasting, which can help investors achieve “buy at a low price and sell at a high price”. Many scholars are focusing on how to increase investors' returns and reduce their risks. This study takes stocks in the United States and Taiwan as the research objects, and historical data, futures, and options as the data set, in an attempt to find a less risky and more rewarding method of stock trading decisions. Long short-term memory neural networks (LSTM) are used to study stock price fluctuations. The Kelly criterion for fund management is used to calculate the optimal investment ratio, and a stop loss strategy based on double thresholds is added so that investors can sell within a certain period when the stock price falls to a certain range, thereby reducing investors' risks. The particle swarm optimization algorithm (PSO) is used to optimize the critical values of trading threshold and stop loss range. The experimental results show that the stop loss strategy based on double thresholds can effectively reduce investors' risk. The addition of leading indicators such as futures and options can increase the accuracy of stock prediction and increase the return of investors.